{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.0060087442398071, "min": 1.0060087442398071, "max": 2.8698716163635254, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9605.37109375, "min": 9605.37109375, "max": 29453.4921875, "count": 20 }, "SnowballTarget.Step.mean": { "value": 199984.0, "min": 9952.0, "max": 199984.0, "count": 20 }, "SnowballTarget.Step.sum": { "value": 199984.0, "min": 9952.0, "max": 199984.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 12.554936408996582, "min": 0.3183857798576355, "max": 12.654862403869629, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2448.212646484375, "min": 61.766841888427734, "max": 2577.71875, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 8756.0, "min": 8756.0, "max": 10945.0, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06828265739657617, "min": 0.06095894481438924, "max": 0.07599452281369047, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2731306295863047, "min": 0.2504376043518777, "max": 0.36258783095599584, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.2107161518697645, "min": 0.12479623987604224, "max": 0.28935926517142974, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.842864607479058, "min": 0.49918495950416897, "max": 1.3715614959889768, "count": 20 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 8.082097306000005e-06, "min": 8.082097306000005e-06, "max": 0.000291882002706, "count": 20 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 3.232838922400002e-05, "min": 3.232838922400002e-05, "max": 0.00138516003828, "count": 20 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10269400000000001, "min": 0.10269400000000001, "max": 0.19729400000000002, "count": 20 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.41077600000000003, "min": 0.41077600000000003, "max": 0.96172, "count": 20 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.0001444306000000001, "min": 0.0001444306000000001, "max": 0.0048649706, "count": 20 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0005777224000000004, "min": 0.0005777224000000004, "max": 0.023089828, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 25.181818181818183, "min": 3.409090909090909, "max": 25.181818181818183, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1108.0, "min": 150.0, "max": 1378.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.181818181818183, "min": 3.409090909090909, "max": 25.181818181818183, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1108.0, "min": 150.0, "max": 1378.0, "count": 20 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 20 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 20 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1694622184", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./ml-agents/config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1694622652" }, "total": 467.451666437, "count": 1, "self": 0.43737301199996637, "children": { "run_training.setup": { "total": 0.09107210100000884, "count": 1, "self": 0.09107210100000884 }, "TrainerController.start_learning": { "total": 466.923221324, "count": 1, "self": 0.5177793600032601, "children": { "TrainerController._reset_env": { "total": 5.518559630999988, "count": 1, "self": 5.518559630999988 }, "TrainerController.advance": { "total": 460.7486546739968, "count": 18202, "self": 0.26783321099657087, "children": { "env_step": { "total": 460.4808214630002, "count": 18202, "self": 337.46077372900834, "children": { "SubprocessEnvManager._take_step": { "total": 122.7544295259934, "count": 18202, "self": 1.7043838379933902, "children": { "TorchPolicy.evaluate": { "total": 121.05004568800001, "count": 18202, "self": 121.05004568800001 } } }, "workers": { "total": 0.26561820799844327, "count": 18202, "self": 0.0, "children": { "worker_root": { "total": 465.54824815199254, "count": 18202, "is_parallel": true, "self": 221.91781896299463, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.007354161999984399, "count": 1, "is_parallel": true, "self": 0.0049244680000413155, "children": { "_process_rank_one_or_two_observation": { "total": 0.0024296939999430833, "count": 10, "is_parallel": true, "self": 0.0024296939999430833 } } }, "UnityEnvironment.step": { "total": 0.08359280999999896, "count": 1, "is_parallel": true, "self": 0.0006283220000113943, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00040306599998984893, "count": 1, "is_parallel": true, "self": 0.00040306599998984893 }, "communicator.exchange": { "total": 0.07953866500000117, "count": 1, "is_parallel": true, "self": 0.07953866500000117 }, "steps_from_proto": { "total": 0.0030227569999965453, "count": 1, "is_parallel": true, "self": 0.00036207299996249276, "children": { "_process_rank_one_or_two_observation": { "total": 0.0026606840000340526, "count": 10, "is_parallel": true, "self": 0.0026606840000340526 } } } } } } }, "UnityEnvironment.step": { "total": 243.6304291889979, "count": 18201, "is_parallel": true, "self": 10.447899412993195, "children": { "UnityEnvironment._generate_step_input": { "total": 5.149910902001011, "count": 18201, "is_parallel": true, "self": 5.149910902001011 }, "communicator.exchange": { "total": 192.78740995900625, "count": 18201, "is_parallel": true, "self": 192.78740995900625 }, "steps_from_proto": { "total": 35.24520891499745, "count": 18201, "is_parallel": true, "self": 6.395931167991478, "children": { "_process_rank_one_or_two_observation": { "total": 28.84927774700597, "count": 182010, "is_parallel": true, "self": 28.84927774700597 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00011588899997150293, "count": 1, "self": 0.00011588899997150293, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 457.2558811290354, "count": 418746, "is_parallel": true, "self": 9.464269309044141, "children": { "process_trajectory": { "total": 246.71365781499162, "count": 418746, "is_parallel": true, "self": 245.9105329869916, "children": { "RLTrainer._checkpoint": { "total": 0.8031248280000227, "count": 4, "is_parallel": true, "self": 0.8031248280000227 } } }, "_update_policy": { "total": 201.07795400499964, "count": 90, "is_parallel": true, "self": 81.65199352899731, "children": { "TorchPPOOptimizer.update": { "total": 119.42596047600233, "count": 4587, "is_parallel": true, "self": 119.42596047600233 } } } } } } } } }, "TrainerController._save_models": { "total": 0.13811177000002317, "count": 1, "self": 0.0008473829999502414, "children": { "RLTrainer._checkpoint": { "total": 0.13726438700007293, "count": 1, "self": 0.13726438700007293 } } } } } } }